Slashdot Mirror
Handheld Supercomputers in 10-15 Years?
An anonymous reader writes "Supercomputers small enough to fit into the palm of your hand are only 10 or 15 years away, according to Professor Michael Zaiser, a researcher at the University of Edinburgh School of Engineering and Electronics.
Zaiser has been researching how tiny nanowires — 1000 times thinner than a human hair — behave when manipulated. Apparently such minuscule wires behave differently under pressure, so it has up until now been impossible to arrange them in tiny microprocessors in a production environment. Zaiser says he's figured out how to make them behave uniformly.
These "tamed" nanowires could go inside microprocessors that could, in turn, go inside PCs, laptops, mobile phones or even supercomputers. And the smaller the wires, the smaller the chip can be.
"If things continue to go the way they have been in the past few decades, then it's 10 years... The human brain is very good at working on microprocessor problems, so I think we are close — 10 years, maybe 15," Zaiser said."
Before anyone asks. Also you can imagine a beowulf cluster of these, as well as welcome the overlords.
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
Isn't a super-computer a relative term? I mean, I don't know the exact figure but I would that my Dual Core Intel box at home is probably a good deal faster than a super-computer from the 80s. It is probably hundreds of thousands or perhpas millions of times more powerful than the computers used in the Apollo programme. Surely the measure of what is a super-computer and what isn't must be based upon what the fastest machines are in the world at that time.
Perhaps what he means is that what we currently do with supercomputers today will be able to be done with low cost computing. I can certainly see that being true. In fifteen years, it may be possible to adequately simulate nuclear weapons tests, climate models, or protein folding from a run-of-the-mill desktop.
However, the improvements in computing speed will also apply to super-computers. With that extra power you can run more refined models so I can't see how this could obsolete the traditional bulky super-computer.
In short, I can't really understand the super-computer slant of the article. Why not just talk about general-purpose computing instead?
Simon
Today's handheld devices ARE the supercomputers of decades past. Things are always getting faster and smaller. If you took a WinCE device or iPhone back 15 years, you'd blow peoples' socks off.
"We can categorically state we have not released man-eating badgers into the area." - UK military spokesman, July 2007
10-15 years from always, I'll wake up to my alarm clock, powered by cold fusion. I'll stumble down stairs and get the keys to the hover car from the kitchen and grab my hand held supercomputer. On the way to work, I'll play Duke Nukem Forever as my car flies me along the correct path.
My work here is dung.
Sometimes I wonder if in 10 years we will still be using mechanical hard drives.
1-inch multi-terabyte hard drives, but mechanical hard drives never-the-less.
Isn't "supercomputer" a bit of a relative term? Don't we have supercomputing handhelds today, if you look at the original supercomputers?
Warning: Apple/Nintendo fangirl. Likes her electronics cute & cuddly. May be rabid.
Is it really a going to be a Super Computer, given that in 10 to 15 years computers that are larger than this one will be will more than likely be much faster? A little sensational really...
10 - 15 years till they are made. 100 - 150 years till they travel back in time, killing everyone named Sarah Connor Will they still run Linux at that point?
There are two kinds of people - those who are radioactive and those who have already decayed..
Most of todays cellphones are the super computers of yesteryear. What's really interesting though is what tomorrows super computers will be.
They will come up with a better name than BrainPal.
If brevity is the soul of wit, then how does one explain Twitter?
... the smaller the chip can be".
Isn't it also true that the smaller the wires, the more likely electron migration will be a problem?
We've already had a joke here saying Vista won't run at full speed, but I think there's a kernel of truth, there.
If you can put a supercomputer in your hand, it's not a supercomputer. A week ago, we had an article here on a guy who'd wired several PS3s together and called it a supercomputer. Folks didn't agree with the supercomputer designation, even though he was getting flops that would clearly have been supercomputer speed just five or six years ago. It's not speed that defines a supercomputer, it's speed relative to what's commonly available.
If we crunch down machines to incredibly small size, then research institutions will buy one 50 times that size. Every time. What will happen is that that tech (if it's not expensive) will drive PC speeds up, perhaps phenomenally, software development tools will make use of the extra speed to make programming easier at the expense of run-time, and we won't see significant speed increases in the user experience. The user will be able to do more, of course, but he'll be complaining "When I speak into the microphone to tell it to write a three page synopsis of this book in it's library, it stalls and lags, and sometimes I tell it twice, before I get a response, and then it gives me two outputs. This thing is SLOW."
lol wut
No, really. An iPhone is much more powerful than the Cray-1, and probably significantly more powerful than a Cray X-MP. The iPhone certainly has much more RAM and storage than they typical early Crays; I can’t be bothered right now to find out what kind of MFLOP performance an iPhone has.
Cheers,
b&
All but God can prove this sentence true.
...presumably it will be useful to control my flying car.
I predict that within 100 years computers will be twice as powerful, 10,000 times larger, and so expensive that only the five richest kings of Europe will own them.
Sweet informative mod.
i can hold a stack of eight ps3 units in my hand today. http://games.slashdot.org/article.pl?sid=07/10/17/1314221
Oh, the processing power will be there... But we will have redefined what a "SuperComputer" is before then, so the term will change before the power gets there.
A positive attitude may not solve all your problems, but it will annoy enough people to make it worth the effort.
Technically, isn't my cell phone a super-computer by the standards of previous generations? Or is it not a matter of processor horsepower but the size of the bus?
The analogy I've seen comparing big iron midrange and mainframes vs. PC's is "Yeah, the PC is zippy, but it's like a ninja bike. The big iron is like a dump truck. The midrange isn't going to get up to speed as quickly but it's going to be doing a hell of a lot more for the effort."
Kwisatz Haderach
Sell the spice to CHOAM
This Mahdi took Shaddam's Throne
We won't have handheld supercomputers ever. If you have a handheld supercomputer, you can have a cluster of them, or better yet, a desktop sized computer so you're not wasting space with screens, batteries, and casings. Until the input/output problem for tiny devices is solved, handhelds will be PDAs and game devices (maybe doing neat things that today's desktops do, but very few will use them to try to crack the latest encryption algorithm).
Maybe you will be able to hold a machine that matches a current super computers power in your hand in ten years but there is one thing it won't be able to do in your hand - run.
Extrapolating power consumption over the last ten years would seem to indicate that this "super computer in your hand" would probably be glowing red hot. Before we increase computing power much more we need to get a handle on efficiency.
I used to have a better sig but it broke.
And we still can't find a decent place to get them fixed when they're broke.
To live without killing is a thought which could electrify the world, if men were capable of staying awake long enough.
The real factor here is Moore's Law. When you can put more and more transistors on a single chip/dye, you have two only have a few (basic) options - (using it for more integrated peripherals,) using it for more cache/memory, or using it for adding more cores.
It is arguable which method will yield faster performance/more power for a given application, but no doubt - as just a few years ago multi-processor (core) machines were reserved for "high-end" or "elite" applications - today, basic workstations or even laptops have them.
Moore's law and basic math can tell you how this will (probably) translate into smaller devices.
So how are we going to have thousands of processors in a little PDA, each having the futuristic equivalent of millions of cores, or even quantum cores. And isn't there some law of entropy that will eventually require a certain amount of processing to require a certain amount of energy in order to not go towards less entropy? So in 15 years we will have processors small enough to fit thousands in a small pda, with a building sized liquid helium cooling through superconducting heatsinks, and a small power plant for energy, right?
...is that all their number crunching programs will be written in Fortran 2015.
My first program:
Hell Segmentation fault
Sounds like Fusion power, but always 10-15 years away!
The 1970s called. It wants its hype back.
-- If you try to fail and succeed, which have you done? - Uli's moose
What was that that just flew by me? Oh yeah! It was the vapor that is this article!
The game.
You'd like to have a PDA with good double precision (64bit) floating point performance then, which most do not have. But an AMD Geode - as used in the OLPC project - could fit the description.
send + more == money?
They'll patent their invention. People will start using it when the patent runs out. I think a corollary to Murphy's law is in effect here.
There are a lot of things whose patent ran out before people actually started using them. Spread spectrum comes to mind. It was patented circa WW2. Nobody used it for about thirty years. Now we can't live without it.
What was a supercomputer when I got my firs computer (A Sinclair 1mz w/ 4k memory) is now called a "mobile phone".
=mcgrew
mcgrew's razor: Never attribute to stupidity that which can be explained by greedy self-interest
By the time such computer exist, Vista's successor will use all of that computing power.
If you delay pleasure infinitely, the pleasure will be infinite. (YM)
TWW
"Encyclopedia" is to "Wikipedia" what "Library" is to "Some people at a bus stop"
I already have a supercomputer on my desk, relative to the standards of 10-15 years ago.
Remember, You are unique...just like everyone else.
Here will be an old abusing of God's patience and the king's English.
You Insensitive Clod!!!
{...sniff....}
A goal is a dream with a deadline
See also: flying cars, home grown clothing, and a Democrat who cuts taxes. :)
Think: is a handheld supercomputer going to be cheap? Was the first X-box cheap? How about the first PlayStation 3? If it's not cheap, it's a novelty. And what would you do with that power?
Here's the point: the technology's getting ready to take a jump. But something held in your hand isn't friendly to input, would have (at best) a complex printout. Just try editing your company's mission statement on your cellphone, and you'll see what I mean.
But as a tech-bump? Sure! Why not? But thinking we're going to walk around with 10x the desktop power on a wristwatch is just silly. It doesn't belong there, not yet. Where are the Pentiums and P2's and P3s? Not on our wrists...still on a desk or in a laptop. The form factor doesn't work.
As for tech on the desk...how many of us really use this? A full 90%+ of us on the globe use our computers for email, browsing, document prep and playing media. If we could multiply the power of our CPUs 100-fold, what would we do different? Not much. That's what makes Linux so attractive, that and the no-illegality, no virus stance.
Oh, sure- research organizations could farm it out, no doubt. Even local weather-casters could have their own 'models' too. But until Windows2020, no consumer's gonna have a reason to waste that much power, held in their own hand: this is tech-hype.
--- For a good time mail uce@ftc.gov
My DS is several times more powerful than my old 486sx. (Though still has the same amount of RAM)
"I am the king of the Romans, and am superior to rules of grammar!"
-Sigismund, Holy Roman Emperor (1368-1437)
Am I the only one who worries this miniscule supercomputing power will be used in a future version of FURBY?!!!
An annoying toy with more intellect than its owner... it'll plot against us all... we'll be overun by a mob of attention seeking robotic creatures that just recite Pi to ten billion decimal places, over and over and over again!!
The horror!
As several people have pointed out, the notion of supercomputer is relative. The thing that you can hold in your hand today us usually far less capable than what you can hold in a room today.
With that in mind we can assume that the author is referring to the idea of having something with the power of today's supercomputers in your hand within x number of years. Even with that understanding it seems that today's supercomputers aren't capable of a very useful level of general intelligence and they are not concerned with addressing the technological issues associated with audio and visual interfaces that would help us to avoid automobile accidents and other problems when we are relying on these devices. Only some of the technological problems with audio visual interfaces are related to component density and speed.
Regarding Moore's law as it relates to these issues it is important to realize that doubling your component density and increasing your speed correspondingly is not likely to increase functionality in the same proportion. For many applications that require intelligence in a device it seems that something like the logarithm of the density and speed is the relevant performance measure. Then there is the issue of user interface software technology. Because of these types of issues I'm usually not interested in updating any of my computers unless there is a crudely validated performance factor of at least 2 or unless there is a big improvement in the user interface technology that requires a hardware upgrade. In the case of server technology I can understand getting spun up over a 10% performance increase but for most personal use a factor of at least 2 without a significant change in the user interface seems to result in no noticeable productivity improvement. Has anyone done a study of this ?
I have always had trouble with people in the tech industry generally speaking, that refuse to be pedant about their terms and definitions. While it might technically be true that your desktop computer is as powerful as supercomputers of years past, they do not qualify as 'supercomputer' for one reason: The purpose of said computer. Supercomputers are designed to tackle certain problems, or be capable of it. Your desktop machine is designed to be a general purpose machine capable of running .... ughh... Windows. Show me 250,000 dollars worth of hardware designed to run windows and I'll give you the supercomputer on your desktop designation.
The clever use of clustered game controllers does go some way towards 'mini supercomputer' status, but might I suggest we give it another designation? high performance vector computer, high performance RISC computer etc.
When network computing architecture allows for 25000 cells working together across a network to create hitherto unknown FLOPS speeds, perhaps we can come up with other designations... like SkyNet or something.
In the meantime, I leave you with a car analogy:
If you invent an engine that would make a Mazda Miata seem to perform like a fuel dragster, you still would not call it a fuel dragster. Even if you can get 650BHP out of your new miata, it will still not work correctly/well on a 1/4 mile drag strip.
Mind you, I'm all for a super high performance RISC machine embedded in my cellphone just the same.
Support NYCountryLawyer RIAA vs People
Will they let me run my All-In-Wonder video card under Linux?
I recently picked up a Nokia 770. This device came out a couple years ago, say 2005. In 1985, I worked with a CDC Cyber 205 supercomputer. So, this is really 20 years, not 15. I have benchmark results for both, so why not compare?
The Nokia has 64 MB RAM. The '205 had 16 MB RAM. The Nokia kicks scaler code at about 40 to 100 MIPS. The '205 kicked scaler code at 35 to 70 MIPS. The Nokia has a DSP, which seems to be able to kick about 200 MFLOPS (i could be wrong). The '205 had twin vector pipes with a peak performance of 200 MFLOPS each, but it was rare to get more than 80% of that. My point is that they're comparable. The Nokia came with 192 MB file store, but now has 2.1 GB, and can mount my desktop filesystems over WiFi with better than 1 MB/sec throughput. The '205 had about 1 GB disk, and could mount mag tapes. Both sport native compilers for C, Fortran, etc. The Nokia was about $150. The '205 was about $15,000,000. That's a factor of 100,000 improvement in price/performance. The Nokia runs on batteries and fits in my shirt pocket, with the form factor of my old Palm Pilot. The '205 had a motor-generator power conditioner (the flywheel acts like a battery in power failure) and fit in large machine room with temperature and humidity carefully controlled.
Would i call the Nokia a supercomputer? No. Supercomputers cost more than a million dollars when they are new. Would i build a beowulf cluster of Nokia's? Maybe. With WiFi, one might put together an ad-hoc grid pretty easily. I only have one. But my 4 year old desktop is more than 30 times faster, so it's going to be hard to justify from a pure performance standpoint. Yes, my desktop has better price/performance than the Nokia.
I've not yet run a SETI@Home unit on the Nokia. It'd be much better than the one i ran on the 486/33...
-- Stephen.
600 MHz, fits in your pocket? That's a handheld supercomputer.
The way I love my computers, a handheld supercomputer is made for incessant fondling.
Know your pads. One time pad: good for cryptography. Two timing pad: where to take your mistress.
What is correct? Both.
By alrights todays average computers ARE supercomputers, you just have to measure them against the supercomputers of the past.
By that same token you will NEVER have a handheld superocmputer because by simply combining a couple of them together you would have an ever more powerfull computer.
So the article basiclly states, in the future you will have more processing power then you have today. Mmm, yeah, that might happen.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
One Friedman Unit, also known as "one Friedman" or "one F.U.", equals six months. The term is a tongue-in-cheek neologism coined by blogger Atrios (Duncan Black) in reference to the discovery by Fairness and Accuracy in Reporting of journalist Thomas Friedman's repeated use of "the next six months" as the time period in which, according to Friedman, "we're going to find out...whether a decent outcome is possible" in the Iraq War. FAIR cited his use of the phrase as early as 2003. http://www.sourcewatch.org/index.php?title=Friedman_(Iraq_War_time_unit)
^^
This should come as no great surprise considering the Apollo lunar missions were controlled with computers that had less power than the average laptop has these days.
My wonder on this is how are they going to dissipate in such a small package?
+++++++++++++++++++++++++++++++++++++++++++++++++
Aye, lad, of course you can imagine a beowulf cluster of these. But that's the easy part. Everyone can do that these days. Why my nephew could imagine a beowulf cluster on a good day, and he's a toddler.
Now try imagining cooling it. That's the real challenge. That's what makes grown up men cry like little girls.
I mean, look 15 years back in time. That was in 1992. We still had desktop cases without fans (except maybe on the PSU, though even there not on all), CPUs without heatsinks (and in fact, the chip even included in a big slab of resin or such and it made no difference to cooling anyway), and computers could safely run on PSUs whose wattage was a 2 digit number. We also still had RAM fast enough that you didn't need a CPU cache (nor had a transistor budget for it, anyway). And we thought that a program that takes a whole floppy is bloated. Etc.
So I'm going to put on my wizard hat and rub the ol' crystal ball, and tell you how I see computing in the future.
- seein' as case fans started from none, and now we're at two or more 120mm fams and ducts per case, I see the computer of the future as a cube, whose whole face (or maybe side) is one big 14" fan (yes, inch, not cm) blowing air in and another in the back blowing it out. In fact, it will all be one big square wind tunnel, or an oversized hair dryer.
You'll alos be advised to not put anything more flammable than asbestos behind it, and fence it so your cat or toddler can't get behind the computer and get cooked.
- a decent power supply will be around 3-4 kilowatts, but Nvidia will recommend 5 kW for their latest graphics card, more if you run a SLI setup.
- or maybe water cooling will become the standard, and the computer will nicely double as a samovar and espresso machine.
- heatsinks will be made of pure silver. And ATI will still need something that sounds like a jet fighter at takeofff to keep their GPU at only 90C.
- continuing the trend, graphics cards will keep needing increasingly more dedicated power connectors, and increasingly more pins on them. We started at 1 with 4 pins, and now we're at "ATI won't activate this or that function if you don't have 8 pins on the second power connector." I foresee that in 15 years we'll be at 6 power connectors with 16 pins each, just to bring enough current to the graphics card.
- still noone will have invented a better use of all that silicone than adding yet another core, so given that 15 years is no less than 10 cycles of Moore's Law, you'll have anywhere between 2048 and 4096 cores in your PC. More time will be spent passing messages between those and serilizing access to data, in algorithms that were never meant to be massively parallel, than actually computing the useful part. People will still argue that it's the fault of game programmers that they don't split processing 5 NPCs between 2048 CPUs, or for that matter, the fault of compiler makers that they insist on reading the file sequentially instead of each core processing every 2048'th line of the file.
- We'll be up to, oh, maybe DDR9, or maybe some newer standard. It still won't have lower latency in nanoseconds than the old SDR, but people will still buy it based on theoretical burst speed. Even more ridiculously larger caches will be needed just to keep all those cores working at all, instead of spending thousands of cycles waiting for the RAM to finally answer. On the bright side, though, we'll have enough budget of transistors form 2 to 4 gigabytes of cache on the CPU.
- As that trend continues, eventually the disparity between RAM and CPU will get so high that it will be entirely feasible to skip RAM completely, and run the programs off the hard drive and the CPU's L3 cache. (The disparity between CPU speed and RAM latency is _already_ as big as that between the 8088 in the IBM PC/XT and the hard drive it had.)
- People will still take the extra power as an invitation to write bloated and slow code. So even th
A polar bear is a cartesian bear after a coordinate transform.
There was nothing anywhere even remotely capable of 1 teraflop in the 70s. All it takes is two seconds of thought and just a tiny bit of common sense to realize this. CPUs were measured in KHz back then, thousands of them would together be a fraction of a current desktop CPU. The definition of supercomputer used to be measured in MFlops, then GFlops, and only just recently TFlops. As processing power increases, the definition of supercomputer is increased as well.
They'll still be about the same RELATIVE TO desktops, servers, and other machines... handheld devices.
Hell, my palm pilot way outpowers my CoCo II. Are any of you OLD ENOUGH to remember the CoCo??
-- I am. Therefore, I think!
Several years ago, I benchmark a Palm Tungsten handheld at over 3 megaflops (double precision floats), which was around the linpack performance of a CDC 6600, the first supercomputer designed by Seymour Cray. There are already lots of much smaller cell phones which can beat that.
My cell phone (motorola Q) is better in every respect except screen size then my first computer (486 dx)
Phone
CPU: PXA272 312 MHz
memory: 64 mb
Drive: 64 mb built in flash 1gb mini-SD card
First comp
CPU: 486 dx 33mhz
Memory: 8 mb ram
drive: 350 mb HD
It's not a huge leap to assume todays desktop will be tomorrows mobile device 20 years down the line.
"There are more things in heaven and earth, Horatio, than are dreamt of in your philosophy."
He's got a pretty bizarre definition of "supercomputer." I've always understood supercomputers to be the fastest, craziest computers currently available. Obviously, this changes over time. I propose that a hand-held computer BY DEFINITION cannot be a "supercomputer." It may be a very, very fast computer. But take thousands of such hand-held "supercomputers" and slap them together, that's a REAL supercomputer. Just like it's always been.
In 1980, many of our desktop machines would have been considered "supercomputers" on the basis of their speed and memory capacities. But supercomputers THEY AIN'T, at least not in 2007.
A supercomputer is, and probably always will be, a physically large, hot-running machine in the basement of a research lab somewhere.
Speaking of scorch marks on the wall behind the computer, Arthur C. Clarke's Venus Prime had a Steam Cooled Nano-Supercomputer. It looked like one of those aerators you screw on to the end of the faucet on your kitchen sink. And that's what the main character did with it. The water would vaporize as steam, dissipating enormous amounts of heat.
Actually, it is the much greater rate of deceleration upon impact that matters here. You can accelerate by 9.8m/s^2 into relativistic speed and be just fine unless you come to an abrupt stop, so you're all arguing the wrong side of the issue.
;)
(What? There was a joke there? Where?
I lost my sig.
Indeed ... at the time I started in computing "the" Supercomputer was the CDC6600
(having just overtaken the Atlas and Stretch).
... and in those days I was proud to be allocated 2 minutes CPU time per week on the 6600.
Hanging on the belt round my waist I now have:
A mobile phone;
A PDA;
An MP3 player;
and a digital camera.
Each of these has - and arguably needs - significantly more compyer power than that old CDC6600.
60 megaflops
64 Megabytes
My cellphone or iPod alredy beats this.
Yes, the PS3 cluster is a supercomputer - by today's marketing definition of a supercomputer. I've been watching technology export law since the Kremvax days, back when the US government was actually more worried about Commies getting high technology rather than using leftover cold war ideology as a way to keep the US from going non-wiretappable during the 90s, and export law had to adapt their definitions of supercomputers largely because of how heavily the exportocrats got taunted when it became obvious that the Playstation 2 would be an illegal-to-export supercomputer. There's a good article from CNET about the status in 1999 - the permitted speeds varied by customer country and military/civilian application, but they went from roughly 2000 MTOPS in 1996 to 7000 in 1997 to 20000 in 1999 (that's million theoretical operations per second, so roughly bogoMIPS) to some number of "weighted teraFLOPS" in 2006.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Ah, a sauna and computer room in one. Nice. I can see it now, being in the underwear and sweaty in front of the computer for a WoW raid won't be some insult thrown around by non-gamers, but actually normal and healthy.
Ya know, it might even help get laid. Once you have a computer like that, you just need to find an excuse to show her something on the computer, and then you can casually mention, "you might want to take off some of the clothes before I start it, or you'll get them all sweaty." Might even work, now that I think about it. I was reading somewhere that if you get her to take her shoes off, the rest is somewhat easier. I figure that by the time you got her to remove her blouse, skirt and stockings because you're about to start the sauna, it should be even less of a struggle ahead
Damn... now I wish I had one of those back in university, when I was doing the asignments of anyone who was a female and willing to ask...
I must admit, that beats my samovar idea handily. Well done
A polar bear is a cartesian bear after a coordinate transform.
If it existed 15 years ago, it would have been considered a super computer.
So basically, this article is saying "Moore's law is going to continue to work for the next 15 years, just as it has worked for the past 15 years."
Nothing to see here boys, move along.
excitingthingstodo.blogspot.com
The power sources for the computers, however, are 30 years away.
Depending on whether you define "supercomputer" statically (as a Cray-1 speed) or dynamically (as a machine on or near the TOP500 list), you'll find that handheld supercomputers are either already here or else will never get there. In the "Already here" camp, a Cray-1 is about as fast as a Pentium 133; I've got a GPS wristwatch that's about 5 years old, and while my old Palm handhelds only have Mac Classic levels of horsepower, many of the media-focused handhelds have ARM chips running several hundred MHz so they're in range; even the newer iPods are pretty close.
On the other hand, if you define a Supercomputer dynamically, then pretty much by definition you're not going to get a handheld into the Top500 list because somebody who doesn't have that design constraint can make a faster machine for less money, and therefore it wouldn't make sense to do that. (Perhaps that'll change after the Great Nanotech Singularity transforms us into uploaded post-humans, but at that point we probably won't care about fitting computation into hands made out of meat and the Top 500 supercomputers will be recycled planets, so it'd be a short-lived niche market in between if it happens at all....) A less silly scenario that could possibly happen is that some nanotechish breakthrough makes it possible to grow large areas of molecular-sized computation elements efficiently but doesn't make interfacing to them easy, so it could be more efficient to make the whole computer out of nanoscale stuff with only a network connection and power feed, in which case it might make sense to have palm-sized supercomputers (or palm-sized CPU/storage units with big air conditioners supporting them.) Palm-sized doesn't necessarily mean hand-held - if it needs to run in liquid nitrogen, you're not going to carry it around even though it's small enough to do so.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
Sounds nice, but where's my goddamn flying car?!
<sig> </sig>
I'm not sure I see where all of this is fitting into "putting a super computer in your hands." If one is talking about overall processing capability and clustering cores, thats all CMOS on-die design. I'm not seeing where these nanowires tie in. Increasing our on-chip computational ability will have more to do with overall CMOS scale down. Want a whole computer on a chip? We've already got plenty of microcontrollers. Want one really fast? Make a design on a 45nm process instead of 180nm. This isn't some kind of miracle discovery that is going to save us from the CMOS brick wall coming up within the next couple of decades. With the next generation of scale down (or even currently at the 45nm process) we have Layer 1 metal lines the same width as this nanowire tech. I suppose you could say that you could shrink down the entire system and go for a SoC approach, but even then, you're more constricted by die sizes, not wire widths. And if you go with a Die-on-Die approach, why use complex nanowires when you can get the same sizes from through-die vias. Of course, this would be a different story if the values given in the article are incorrect and the nanowire tech scales down to the picometer range (or single digit nanometer width). If that is the case, after the large fabrication issues that come with introducing new chemistry to the process are addressed, then this could allow for much more area on the Die and allow for greater transistor densities.
I see comments like this and I think...now if its a hand-held device, will it really be a supercomputer? I think what hes really saying is that the power of "todays" supercomputers will be in your hand...which is a safe bet. I still think the real supercomputers will be housed in some large complex as always, one of which will probably encompass several magnitudes of the power of all the ones we now have on the top 500 list. I say "small supercomputers" will always be an oxymoron by definition of a supercomputer, that is my prediction.
Time to bring out the super-duper computer!
Have gnu, will travel.
By then there will be no other OS!
http://fakesteveballmer.blogspot.com
Of course, you realize, that once this happens it won't qualify as a supercomputer anymore.
Paul Anderson
"I drank WHAT?!" -- Socrates
Otherwise, by the scale of what was available in the mid '80s, we've already got handheld supercomputers in the guise of the PalmPilot and various Windows and Linux handhelds.
"Supercomputer" is a moving target which will likely never wait for your hand to catch up to it.
Sometimes boldness is in fashion. Sometimes only the brave will be bold.
This is ridiculous next they will be telling us there will be 'pocket calculators' that can help you solve mathematical problems while one is on the move.
What's the big deal here? Handhelds already are far more powerful than the supercomputers we had when I was an undergraduate. There's a natural progression here: a certain level of processing power is exceedingly expensive at first, and eventually comes down to where it's expensive, cheap, and finally to where you can't get anything that wimpy by buying cheap from Dell.
"When you have eliminated the unacceptable, whatever is left, however improbable, must be the truthiness" - Holmes
From Fallout. I don't want my handheld to mop the floor with me at chess!
Tomorrow's wrist watch will have more power than today's super computers - This concept somewhat reminds me the short story "The last question" by Isaac Asimov.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
*picks up his cell phone* Did you hear? They say that ten or fifteen years from now there will be powerful computers so small that they can fit in your hand! Just imagine a tiny little processor, speaker, screen, keypad, microphone, battery...heck, even an antenna for wireless communication.
To (basically) quote Will Smith, "You are the DUMBEST....smart person I have ever seen."
are more interesting than hand-held.
The supercomputer is needed so you can plug it into the flying car (which is only 5 years away), so that it can serve as an onboard computer.